Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cyrusagents/cyrus/release-core-testnpx skills add cyrusagents/cyrus --skill release-core-testgit clone --depth 1 https://github.com/cyrusagents/cyrusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cyrusagents/cyrus/release-core-test)<a href="https://agentmods.dev/skills/cyrusagents/cyrus/release-core-test"><img src="https://agentmods.dev/badge/skills/cyrusagents/cyrus/release-core-test.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.01509 |
| Opus 5 | $0.00057 | $0.00754 |
| Sonnet 5 | $0.00023 | $0.00302 |
| Haiku 4.5 | $0.00011 | $0.00151 |
Grade A, and why
release-core-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Core (Test)
Publish ONLY the cyrus-core package (and claude-runner if needed) as a dev/test prerelease to npm under the test dist-tag. This is a developer convenience for iterating on cyrus-core without going through the full release flow.
What this skill does NOT do
This skill is intentionally minimal. It does NOT:
- Update
CHANGELOG.mdorCHANGELOG.internal.md - Create a git tag
- Create a GitHub release
- Move any Linear issues
- Open a pull request
- Commit the version bump (the bumped
package.jsonis left as a local working-tree change)
It also does NOT publish any other workspace package (no edge-worker, no cyrus CLI, no linear-event-transport, etc.). The only exception is claude-runner, which is republished if and only if its workspace:* reference would otherwise resolve to an unpublished version (see step 3 below).
Workflow
1. Install dependencies from repo root
pnpm install
2. Build all packages from repo root
pnpm build
Building all packages ensures workspace:* dependencies are resolved before publishing.
3. Determine whether claude-runner needs republishing
cyrus-core depends on claude-runner via workspace:*. When cyrus-core is published, that workspace:* is rewritten to the version currently in packages/claude-runner/package.json. If that version isn't actually on npm yet (because claude-runner has local changes since its last publish), consumers installing cyrus-core@test will fail to resolve the dependency.
Run both of these deterministic checks:
# (a) Is the local claude-runner version already on npm?
LOCAL_CR=$(node -p "require('./packages/claude-runner/package.json').version")
npm view "cyrus-claude-runner@${LOCAL_CR}" version 2>/dev/null
# (b) Does claude-runner have uncommitted/unpushed source changes since its last publish?
git diff --quiet HEAD -- packages/claude-runner/src packages/claude-runner/package.json && echo "clean" || echo "dirty"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 139 lines · 114 tokens per session scan A 87ce74a5bc12
release-core-test is a skill published in the GitHub repository cyrusagents/cyrus (797 stars, last pushed today), licensed Apache-2.0. It adds 114 tokens to every session and 1,509 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
release
Prepare and publish stable Agent Lightning releases through the repository's version bump, pull-request checks, merge, tag, PyPI trusted-publishing, and versioned-documentation workflows. Use when asked to plan, cut, verify, or explain a release; treat nightly TestPyPI builds as a separate path.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
bootstrap-repo-analysis
First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the…
herdr-pre-release-audit
Audit herdr release readiness by comparing commits since the base release against next-release changelog and docs. Use when asked to run or apply the repo's pre-release audit, validate docs/next before release, inspect issue refs that release CI will close, or finalize release docs for herdr.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
write-oep
Draft an Open SWE Enhancement Proposal using the repository's OEP process and template. Use when the user asks to create, write, or propose an OEP or invokes /write-oep.